Brandon Rothrock
Jet Propulsion Laboratory, California Institute of Technology
Papers
10
Total Citations
497
H-Index
8
About
Brandon Rothrock is a researcher whose work spans the intersection of computer vision, human-robot interaction, and autonomous systems. His research tackles some of the most pressing challenges in modern robotics: enabling machines to understand human behavior, communicate transparently, and navigate complex real-world environments. Rothrock's most influential contribution is his pioneering work on privacy-preserving activity recognition, which developed computer vision techniques capable of recognizing human activities from extreme low-resolution imagery—protecting individuals from invasive surveillance while still enabling helpful robotic assistance. This work has accumulated over 200 citations across related publications. His 2019 paper on explainable robot behavior (132 citations) proposed frameworks for helping machines articulate their decision-making processes, directly addressing one of AI's greatest barriers to public trust and adoption. Beyond human-centered AI, Rothrock has contributed to robotic manipulation through imitation learning, autonomous planetary rover systems through NASA JPL's MAARS project, gesture-based human-robot communication using synthetic training data, and natural language grounding for field robots. His work on vegetation traversal further demonstrates his commitment to practical robot deployment in unstructured environments. Collectively, his research reflects a vision of robots that are not only capable and autonomous, but trustworthy, safe, and genuinely collaborative partners for humans.
Research Focus
Key Achievements
Top Papers
- 1Privacy-Preserving Human Activity Recognition from Extreme Low Resolution147 citations · 2017
- 2A tale of two explanations: Enhancing human trust by explaining robot behavior132 citations · 2019
- 3
- 4Privacy-Preserving Human Activity Recognition from Extreme Low Resolution59 citations · 2016
- 5Vision-Based Gesture Recognition in Human-Robot Teams Using Synthetic Data30 citations · 2020
- 6MAARS: Machine learning-based Analytics for Automated Rover Systems29 citations · 2020
- 7
- 8
- 9Modeling and traversal of pliable materials for tracked robot navigation8 citations · 2018
- 10